论文标题
用适当的重复单词生成重复
Generating Repetitions with Appropriate Repeated Words
论文作者
论文摘要
重复是一种反应，可以在对话中重复上一位演讲者的话语中的单词。语言学研究中的调查，重复对于与他人建立信任至关重要。在这项工作中，我们专注于重复生成。据我们所知，这是解决重复产生的第一种神经方法。我们提出了加权标签平滑，一种平滑方法，用于明确学习在微调过程中重复哪些单词，以及一种重复评分方法，可以在解码过程中输出更合适的重复。我们进行了自动和人类评估，涉及将这些方法应用于预先训练的语言模型T5来产生重复。实验结果表明，我们的方法在两种评估中的表现都优于基准。
A repetition is a response that repeats words in the previous speaker's utterance in a dialogue. Repetitions are essential in communication to build trust with others, as investigated in linguistic studies. In this work, we focus on repetition generation. To the best of our knowledge, this is the first neural approach to address repetition generation. We propose Weighted Label Smoothing, a smoothing method for explicitly learning which words to repeat during fine-tuning, and a repetition scoring method that can output more appropriate repetitions during decoding. We conducted automatic and human evaluations involving applying these methods to the pre-trained language model T5 for generating repetitions. The experimental results indicate that our methods outperformed baselines in both evaluations.
